7 papers
What Actually Makes Correlation-Based SSL Distillation Noise-Robust? A Mechanistic Correction
Fabian Ritter-Gutierrez, Nancy F. Chen, Eng Siong Chng
Self-supervised learning (SSL) speech models are accurate but large. Knowledge distillation compresses them, but the student loses the teacher's noise robustness. Correlation-based…
ASTAR-NTU solution to AudioMOS Challenge 2025 Track1
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +3
Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically pr…
A correlation-permutation approach for speech-music encoders model merging
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jeremy H. M Wong +3
Creating a unified speech and music model requires expensive pre-training. Model merging can instead create an unified audio model with minimal computational expense. However, dire…
Beyond Classification: Towards Speech Emotion Reasoning with Multitask AudioLLMs
Wenyu Zhang, Yingxu He, Geyu Lin +9
Audio Large Language Models (AudioLLMs) have achieved strong results in semantic tasks like speech recognition and translation, but remain limited in modeling paralinguistic cues s…
Distilling a speech and music encoder with task arithmetic
Fabian Ritter-Gutierrez, Yi-Cheng Lin, Jui-Chiang Wei +4
Despite the progress in self-supervised learning (SSL) for speech and music, existing models treat these domains separately, limiting their capacity for unified audio understanding…
Dataset-Distillation Generative Model for Speech Emotion Recognition
Fabian Ritter-Gutierrez, Kuan-Po Huang, Jeremy H. M Wong +4
Deep learning models for speech rely on large datasets, presenting computational challenges. Yet, performance hinges on training data size. Dataset Distillation (DD) aims to learn…
Noise robust distillation of self-supervised speech models via correlation metrics
Fabian Ritter-Gutierrez, Kuan-Po Huang, Dianwen Ng +4
Compared to large speech foundation models, small distilled models exhibit degraded noise robustness. The student's robustness can be improved by introducing noise at the inputs du…